Skip to main content

Jeremy Maitin-Shepard: Combinatorial Energy Learning for Image Segmentation

Movies Preview

texts
Jeremy Maitin-Shepard: Combinatorial Energy Learning for Image Segmentation


Published September 2, 2015
SHOW MORE


Talk by Jeremy Maitin-Shepard of UC Berkeley.  Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract
Recent advances in volume electron microscopy make it possible to image neuronal tissue volumes containining hundreds of thousands of neurons at sufficient resolution to discern even the finest neuronal processes. Accurate 3-D segmentation of these processes densely packed in these petavoxel-scale volumes is the key bottleneck in reconstructing large-scale neural circuits.
 

We introduce a new machine learning approach for image segmentation, based on a joint energy model over image features and novel local binary shape descriptors. These descriptors compactly represent rich shape information at multiple scales, including interactions between multiple objects. Our approach, which does not rely on any hand-designed features, reflects the inherent combinatorial nature of dense image segmentation problems. We propose efficient algorithms for learning deep neural networks to model the joint energy, and for local optimization of this energy in the space of supervoxel agglomerations.
 

We demonstrate the effectiveness of our approach on 3-D biological data, where rich shape information appears to be critical for resolving ambiguities. On two challenging 3-D electron microscopy datasets highly relevant to ongoing efforts towards large-scale dense mapping of neural circuits, we achieve state-of-the-art segmentation accuracy.


Language English
Collection opensource_media

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Folkscanomy Electronics: Books on Electronics, Circuits and Processors
by Mitiche, Amar; Ben Ayed, Ismail
texts
eye 286
favorite 0
comment 0
Community Media
texts
eye 158
favorite 0
comment 0
Community Media
texts
eye 373
favorite 0
comment 0
Community Media
texts
eye 2,238
favorite 0
comment 0
Community Video
movies
eye 273
favorite 0
comment 0